hermes-windows-setup
Install and configure a repo-centric Hermes agent workspace on Windows. Covers prerequisites, repo cloning, Python/uv environment, skills system, memory…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
Agents & models
26,316 results
llm-wiki
Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.
overnight-parallel-agent-prompts
Design self-contained prompts for 3-5 terminals to run overnight without supervision. Ensures zero git contention, provider-optimal allocation, and a clear…
auto-loop
Drive a Claude Code session toward a verifiable goal until done or a hard cap fires — autonomous loop, no user intervention. Use for refactor batches,…
delegating-to-otto
Drive Astronomer's Otto agent (`astro otto`) as a delegated sub-agent for Airflow, dbt, and data-engineering work. Use when the user says 'use Otto', 'ask…
seedance-prompt
Construct a production-ready prompt for Seedance 2.0 using the Director's Formula. Use when a user has a clear vision and needs to translate it into a…
seedance-prompt-short
Build, validate, and compress Seedance 2.0 prompts to a hard 2000-character limit using the Five-Layer Stack, @Tag delegation, and the new Compression Engine.…
agent-knowledge
Your long-term knowledge pages. Read them at session start. Create new pages when you learn something worth remembering across sessions. Pages auto-update from…
manage
Lifecycle rules for user-created custom skills — versions and drafts, application modes, publishing, rollback, deletion, scopes, and approvals. Load before…
sandbox
Creates isolated Linux MicroVMs using Vercel Sandbox SDK. Use when building code execution environments, running untrusted code, spinning up dev servers,…
adhoc-skill
Create, refine, or sync user-level skills. Works in the skill's source repo first, then syncs to ~/.agents/skills and fans out symlinks. Use when the user says…
mcp-builder
MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.
vs-brainstorm
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent,…
integrator-sdk
Use this skill whenever working with the Vocdoni Integrator SDK packages — @vocdoni/api-client, @vocdoni/api-voting, @vocdoni/react-providers, or…
pi-delegation
Delegate to named Pi subagents and bounded coding tasks via the pi-subagent MCP tools. Use when the user says "use pi-agent <name>", "use pi-subagent <Name>",…
claude-code-pro
Token-efficient Claude Code workflow. Other skills burn tokens polling tmux every 30s — this one uses completion callbacks and only checks when notified.…
delegate-manager-to-subagents
Manage execution of an approved plan through subagents. Use when the user asks the main agent to coordinate implementation, review, testing, or documentation…
gas-town-workflow
Coordinate agents with Gas Town role mapping and convoy-based task decomposition. Use only when the user explicitly requests Gas Town, convoy workflow,…
hang-check
Watch running background agents for evidence of a genuine stall without killing healthy work. Use for hang checks, stuck or silent subagents, stalled agents,…
skill-writing-guide
Author and improve Agent Skills following the open standard. Use for `SKILL.md` frontmatter, trigger descriptions, progressive disclosure, directories,…
stay-busy
Keep an agent manager productive through safe, evidence-producing follow-on work. Use for `/stay-busy`, idle orchestrators, waiting subagents, or active…
voxel51-agent-setup
Connect a local AI agent (Claude Code, Cursor, or any MCP client) directly to a Voxel51 deployment over MCP, authenticating as yourself with your own account…
agent-tool
Add a new tool/function the AI agent can call (e.g. look something up, hit an external API, perform an action). Use when extending the assistant's…
background-task
Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or…